What is the expected time of release for this release? what are the chances of
it happening in May?
--
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub:
https://github.com/apache/incubator-tvm/issues/4845#issuecomment-612762262
f quantize/dequantize ops
> > being int32? Because, the current implementation for
> >
> > 1. Quantize - limits the inputs to be float32 and output to be (u)i8
> > 2. Dequantize - The input to be (u)int8 and output to be float32
> >
> > Or are you suggesting we shoul
@jackwish, i want to get my understanding correct, when you say
> I was looking into PR #3531 and #3512 , and noticed that the PRs are going to
> support 32 bits quantization.
are you talking about the inputs or outputs of quantize/dequantize ops being
int32? Because, the current implementation f
There are quite a lot of changes here that are depndent on #3531 . I am closing
the PR for now. I will reopen this once #3531 is pushed.
--
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub:
https://github.com/dmlc/tvm/pull/3512#i
Closed #3512.
--
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub:
https://github.com/dmlc/tvm/pull/3512#event-2510690970
@liangfu made the changes you suggested.
--
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub:
https://github.com/dmlc/tvm/pull/3512#issuecomment-512443841
> Mainly organizational issues, please make things consistent with what was
> discussed in #3531
I have addressed the namespace issues and have followed the same convetion as
#3531 in the new commit.
--
You are receiving this because you are subscribed to this thread.
Reply to this email direc
@FrozenGene and @tqchen, any other major comments for the PR?
--
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub:
https://github.com/dmlc/tvm/pull/3512#issuecomment-510561960
@tqchen @FrozenGene @ZihengJiang @zhiics @wweic @eqy
--
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub:
https://github.com/dmlc/tvm/pull/3512#issuecomment-509422639
Rebased to new PR #3512
--
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub:
https://github.com/dmlc/tvm/pull/3457#issuecomment-509421969
Closed #3457.
--
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub:
https://github.com/dmlc/tvm/pull/3457#event-2467657739
The purpose of this PR is to dive deep into the desing of the quantized ops. To
start the discussion I have implemented the Quantize and dequantize op which
are easy to implement. There is one more such
[PR](https://github.com/dmlc/tvm/issues/2351) but there the conversation has
meandered towar
> > We need to add `in_dtype` in the dequantize op as the calculations will be
> > different, especially the range to use.
>
> Guess the input tensor has such information already?
@jackwish, the input data is generally an `Expr` can be `Var` or `IntImm` or
some other type of `Expr`. How will i
> Thanks. Let's lay down the high-level API design for some of the quantized
> operators. A large portion of this is coming from the following relevant
> discussions. Thanks to @jackwish, @FrozenGene and @jnorwood for sharing their
> experiences with quantization, and also @sho
@FrozenGene a clarifying question to your above comment. If we pass in the
output scale and shift can we not compute int32-> int8 by simply adding more
nodes in the graph.
--
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub:
htt
15 matches
Mail list logo
